SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910011135885312 |
|---|---|
| author | Chen, Suzeyu Li, Leheng Chen, Ying-Cong |
| author_facet | Chen, Suzeyu Li, Leheng Chen, Ying-Cong |
| contents | Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding bottleneck, it creates a new challenge for the decoder: how to efficiently aggregate information from a sparse, non-uniformly distributed set of voxel features without resorting to computationally prohibitive dense attention.
In this paper, we propose a novel Prototype-based Sparse Transformer Decoder that replaces this costly interaction with an efficient, two-stage process of guided feature selection and focused aggregation. Our core idea is to make the decoder's attention prototype-guided. We achieve this through a sparse prototype selection mechanism, where each query adaptively identifies a compact set of the most salient voxel features, termed prototypes, for focused feature aggregation.
To ensure this dynamic selection is stable and effective, we introduce a complementary denoising paradigm. This approach leverages ground-truth masks to provide explicit guidance, guaranteeing a consistent query-prototype association across decoder layers. Our model, dubbed SPOT-Occ, outperforms previous methods with a significant margin in speed while also improving accuracy. Source code is released at https://github.com/chensuzeyu/SpotOcc. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04240 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction Chen, Suzeyu Li, Leheng Chen, Ying-Cong Computer Vision and Pattern Recognition Machine Learning Robotics Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding bottleneck, it creates a new challenge for the decoder: how to efficiently aggregate information from a sparse, non-uniformly distributed set of voxel features without resorting to computationally prohibitive dense attention. In this paper, we propose a novel Prototype-based Sparse Transformer Decoder that replaces this costly interaction with an efficient, two-stage process of guided feature selection and focused aggregation. Our core idea is to make the decoder's attention prototype-guided. We achieve this through a sparse prototype selection mechanism, where each query adaptively identifies a compact set of the most salient voxel features, termed prototypes, for focused feature aggregation. To ensure this dynamic selection is stable and effective, we introduce a complementary denoising paradigm. This approach leverages ground-truth masks to provide explicit guidance, guaranteeing a consistent query-prototype association across decoder layers. Our model, dubbed SPOT-Occ, outperforms previous methods with a significant margin in speed while also improving accuracy. Source code is released at https://github.com/chensuzeyu/SpotOcc. |
| title | SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction |
| topic | Computer Vision and Pattern Recognition Machine Learning Robotics |
| url | https://arxiv.org/abs/2602.04240 |